# Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods

arXiv: https://arxiv.org/abs/2305.18156 · HTML: https://mlsanity.com/paper/2305.18156/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction](https://mlsanity.com/paper/1702.04066/) (2017)
- [Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation](https://mlsanity.com/paper/2304.01746/) (2023)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction](https://mlsanity.com/paper/2005.00987/) (2020)
- [Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task](https://mlsanity.com/paper/1804.05940/) (2018)
- [An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction](https://mlsanity.com/paper/1909.00502/) (2019)
- [Corpora Generation for Grammatical Error Correction](https://mlsanity.com/paper/1904.05780/) (2019)
- [Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data](https://mlsanity.com/paper/1903.00138/) (2019)
- [A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction](https://mlsanity.com/paper/1801.08831/) (2018)
- [LM-Critic: Language Models for Unsupervised Grammatical Error Correction](https://mlsanity.com/paper/2109.06822/) (2021)
- [EditEval: An Instruction-Based Benchmark for Text Improvements](https://mlsanity.com/paper/2209.13331/) (2022)
- [A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning](https://mlsanity.com/paper/1907.01256/) (2019)
- [Improving Grammatical Error Correction with Machine Translation Pairs](https://mlsanity.com/paper/1911.02825/) (2019)
- [Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses](https://mlsanity.com/paper/2010.07574/) (2020)
- [Interpretability for Language Learners Using Example-Based Grammatical Error Correction](https://mlsanity.com/paper/2203.07085/) (2022)
- [A Nested Attention Neural Hybrid Model for Grammatical Error Correction](https://mlsanity.com/paper/1707.02026/) (2017)
- [Comparison of Grammatical Error Correction Using Back-Translation Models](https://mlsanity.com/paper/2104.07848/) (2021)
- [The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction](https://mlsanity.com/paper/1906.01733/) (2019)

## Built on by (most cited first, 30 of 37)

- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Prompting open-source and commercial language models for grammatical error correction of English learner text](https://mlsanity.com/paper/2401.07702/) (2024)
- [Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?](https://mlsanity.com/paper/2401.18070/) (2024)
- [GPT-3.5 for Grammatical Error Correction](https://mlsanity.com/paper/2405.08469/) (2024)
- [ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages](https://mlsanity.com/paper/2403.17859/) (2024)
- [mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans](https://mlsanity.com/paper/2406.04215/) (2024)
- [Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency](https://mlsanity.com/paper/2402.15930/) (2024)
- [Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study](https://mlsanity.com/paper/2503.00985/) (2025)
- [gec-metrics: A Unified Library for Grammatical Error Correction Evaluation](https://mlsanity.com/paper/2505.19388/) (2025)
- [Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models](https://mlsanity.com/paper/2404.14914/) (2024)
- [Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction](https://mlsanity.com/paper/2309.11439/) (2023)
- [LLMs in Education: Novel Perspectives, Challenges, and Opportunities](https://mlsanity.com/paper/2409.11917/) (2024)
- [Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?](https://mlsanity.com/paper/2502.09416/) (2025)
- [RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation](https://mlsanity.com/paper/2310.07299/) (2023)
- [Opportunities and Challenges of LLMs in Education: An NLP Perspective](https://mlsanity.com/paper/2507.22753/) (2025)
- [Adapting LLMs for Minimal-edit Grammatical Error Correction](https://mlsanity.com/paper/2506.13148/) (2025)
- [Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction](https://mlsanity.com/paper/2403.17540/) (2024)
- [APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification](https://mlsanity.com/paper/2508.09378/) (2025)
- [MedErrBench: A Fine-Grained Multilingual Benchmark for Medical Error Detection and Correction with Clinical Expert Annotations](https://mlsanity.com/paper/2602.05692/) (2026)
- [Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness](https://mlsanity.com/paper/2404.06714/) (2024)
- [PERCORE: A Deep Learning-Based Framework for Persian Spelling Correction with Phonetic Analysis](https://mlsanity.com/paper/2407.14789/) (2024)
- [Tibyan Corpus: Balanced and Comprehensive Error Coverage Corpus Using ChatGPT for Arabic Grammatical Error Correction](https://mlsanity.com/paper/2411.04588/) (2024)
- [Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2502.08507/) (2025)
- [Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction](https://mlsanity.com/paper/2605.13624/) (2026)
- [How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?](https://mlsanity.com/paper/2606.09334/) (2026)
- [Neural Automated Writing Evaluation with Corrective Feedback](https://mlsanity.com/paper/2402.17613/) (2024)
- [Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction](https://mlsanity.com/paper/2403.19283/) (2024)
- [A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction](https://mlsanity.com/paper/2410.20838/) (2024)
- [Integration of LLM Quality Assurance into an NLG System](https://mlsanity.com/paper/2501.16078/) (2025)
- [Joint Extraction Matters: Prompt-Based Visual Question Answering for Multi-Field Document Information Extraction](https://mlsanity.com/paper/2503.16868/) (2025)

## Abstract (arXiv)

Large-scale pre-trained language models such as GPT-3 have shown remarkable performance across various natural language processing tasks. However, applying prompt-based methods with GPT-3 for Grammatical Error Correction (GEC) tasks and their controllability remains underexplored. Controllability in GEC is crucial for real-world applications, particularly in educational settings, where the ability to tailor feedback according to learner levels and specific error types can significantly enhance the learning process. This paper investigates the performance and controllability of prompt-based methods with GPT-3 for GEC tasks using zero-shot and few-shot setting. We explore the impact of task instructions and examples on GPT-3's output, focusing on controlling aspects such as minimal edits, fluency edits, and learner levels. Our findings demonstrate that GPT-3 could effectively perform GEC tasks, outperforming existing supervised and unsupervised approaches. We also showed that GPT-3 could achieve controllability when appropriate task instructions and examples are given.